Member of Technical Staff, Model Efficiency
Cohere
Cohere is seeking a Member of Technical Staff for their Model Efficiency team, focused on enhancing the performance of machine learning systems, particularly in the context of large language models (LLMs). The role involves optimizing model execution, improving performance metrics, and collaborating with various teams to implement innovative solutions. The company values diversity and offers a remote-friendly work environment.
Qualification
- 5+ years of experience in high-performance, production-quality code
- Strong programming skills in C++ or Python (Rust/Go also welcome)
- Experience with large language models and LLM inference ecosystem
- Ability to diagnose and resolve performance bottlenecks
- Strong bias for action and ability to iterate quickly
Responsibility
- Improve core performance metrics of ML models
- Identify bottlenecks in model execution
- Develop optimizations for lower latency and higher throughput
- Collaborate with modeling and systems teams
- Experiment, measure, and ship improvements in inference efficiency
